检索结果-内蒙古大学图书馆

41st computer graphics international conference, CGI 2024

作者： Jung, Hoijoon Jung, Younhyun Fulham, Michael Kim, Jinman School of Computer Science The University of Sydney SydneyNSW Australia School of Computing Gachon University Gyeonggi-Do Seongnam-Si Korea Republic of Department of Molecular Imaging Royal Prince Alfred Hospital SydneyNSW Australia

ISBN: (纸本)9783031820236

Mixed reality head-mounted displays (mxdR-HMD) have the ability to visualize volumetric medical imaging data in holograms to provide a full 3D perception of volumetric information. An effective user interface, however, has yet to be thoroughly studied. Tangible user interfaces (TUIs) enable interaction with holograms through objects that possess physical properties, which indicate their usage, and enable manipulation across multiple degrees of freedom. The main technological challenge in enabling TUIs on mxdR-HMDs, which are inherently limited in computational resources, is tracking the physical object in a timely and accurate manner and achieving seamless TUI integration. We introduce a markerless TUI employing a handheld planar object (PO) to interact with medical holograms, termed the mxdR hologram slicer (mxdR-HS). Our mxdR-HS enables users to slice the medical hologram to inspect regions of interest in real-time, integrate complementary data, and make annotations. We implemented our mxdR-HS on Microsoft HoloLens 1 – a computationally modest mxdR-HMD. We benchmarked our mxdR-HS against well-known tracking methods in various mxdR usage scenarios. Our mxdR-HS demonstrated a reduction in computational latency but with a marginal decline in tracking accuracy when compared to two marker-based methods. When compared to seven markerless tracking methods, our mxdR-HS improved in both latency and accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Helmet mounted displays

来源：评论

学校读者我要写书评

暂无评论

Accurate Diagnosis by Magnetic Resonance imaging Using Deep Learning

Accurate Diagnosis by Magnetic Resonance Imaging Using Deep ...

引用

2024 international conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Rengarajan, A. Ahmed, Zahid Pandey, Rajendra P. Department of Computer Science and Information Technology Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Teetthanker Mahaveer University Department of Computing Sciences and Information Technology Uttar Pradesh Moradabad India

ISBN: (纸本)9798350383348

deep mastering has revolutionized the field of scientific imaging, providing practical affected person prognosis competencies. A current example is deep studying for Magnetic Resonance imaging (MRI) acquisition, reconstruction, segmentation, and interpretation. Deep mastering-primarily based strategies leverage convolutional neural networks (CNNs) to automatically classify and section not unusual disease areas in MRI scans, allowing particular and correct prognosis. Those computerized strategies can potentially conquer the bottleneck of the complex work-intensive guide segmentation and visualization procedure. Moreover, they can provide an extra complete assessment of complex sicknesses. Through incorporating both the semantic and spatial information of image information, the overall performance of deep-gaining knowledge of-based totally structures for MRI evaluation has dramatically progressed. Moreover, CNN-based total MRI segmentation has proven promise in targeted and effective remedies for numerous diseases, including mind tumors, stroke, and dementia. The demonstration of superior effects in segmentation and classification tasks, in terms of accuracy and efficiency, shows the potential of deep learning-based techniques as an effective device within the automation of MRI analysis. © 2024 IEEE.

关键词： classification demonstration performance prognosis visualization

来源：评论

学校读者我要写书评

暂无评论

Fiblets for Real-Time Rendering of Massive Brain Tractograms

引用

computer graphics FORUM 2022年第2期41卷 447-460页

作者： Schertzer, Jeremie Mercier, Corentin Rousseau, Sylvain Boubekeur, Tamy Telecom Paris Inst Polytech Paris LTCI Paris France Adobe Res San Jose CA USA

We present a method to render massive brain tractograms in real time. Tractograms model the white matter architecture of the human brain using millions of 3D polylines (fibers), summing up to billions of segments. They are used by neurosurgeons before surgery as well as by researchers to better understand the brain. A typical raw dataset for a single brain represents dozens of gigabytes of data, preventing their interactive rendering. We address this challenge with a new GPU mesh shader pipeline based on a decomposition of the fiber set into compressed local representations that we call fiblets. Their spatial coherence is used at runtime to efficiently cull hidden geometry at the task shader stage while synthesizing the visible ones as polyline meshlets in a warp-scale parallel fashion at the mesh shader stage. As a result, our pipeline can feed a standard deferred shading engine to visualize the mesostructures of the brain with various classical rendering techniques, as well as simple interaction primitives. We demonstrate that our algorithm provides real-time framerates on very large tractograms that were out of reach for previous methods while offering a fiber-level granularity in both rendering and interaction.

关键词： CCS Concepts center dot Hardware -> GPUs and graphics Hardware center dot Rendering -> Real-Time Rendering center dot visualization -> Medical imaging

来源：评论

学校读者我要写书评

暂无评论

visualization Analysis of Online Education Based on Vue Framework 24

Visualization Analysis of Online Education Based on Vue Fram...

引用

8th international conference on Electronic Information Technology and computer Engineering, EITCE 2024

作者： Shi, Jinmei Wen, Xinyuan Dong, Chunyang Hainan Vocational University of Science and Technology Hainan Haikou China

ISBN: (纸本)9798400710094

Digitalization of education is one of the major strategies for my country’s current education reform and development, and market-oriented online education companies are one of the frontier practitioners in promoting digitalization of education. The work is based on the Vscode programming tool, and uses the Echarts graphics library and the Vue framework to perform Web front-end data visualization interaction design in a knowledge graph visualization manner. Use the Scrapy crawler framework in Python to crawl data from relevant websites, summarize and analyze the industry status, forward-looking areas and research hotspots of online education worldwide, and show the current development history and industry prospects of the global online education industry. By adding the random forest algorithm, we can deeply analyze the profound impact of my country’s double reduction policy on the development of domestic online education and the establishment of a new generation of industry standards. The relevant literature data of the past ten years from CNKI were exported, and the screened literature data were imported into the bibliometric tool COOC and the visualization software CiteSpace for sorting and analysis, presenting the research status and hot trends in the field of online education industry. Help relevant practitioners, researchers, learners, etc. to enhance their business understanding in the field of online education, and provide reference for the digital transformation of education in educational institutions at all levels and types. © 2024 Copyright held by the owner/author(s).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Spotlight Control for Real-Time Targeting 32

Spotlight Control for Real-Time Targeting

引用

32nd international conference in Central Europe on computer graphics, visualization and computer Vision, WSCG 2024

作者： Heinemann, Mika Benjamin Kernbauer, Thomas Fleck, Philipp Arth, Clemens Institute of Computer Graphics and Vision University of Technology Graz Austria

Off-road heavy machinery such as snow groomers or excavators, often operate in low-light and hazardous environments. In this work, we explore the development of an intelligent camera-spotlight system with automatic and manual control to illuminate points of interest, such as obstacles or individuals at risk. We implement a prototype as proof of concept and integrate our workflow using a standard lighting protocol and a single-board computer. The presented calibration of the camera and spotlight ensures high precision in the desired use cases. In addition to testing the prototype on a real snow groomer, we evaluated its performance in terms of accuracy and repeatability. Overall, we showcase the usability of a commercially available spotlight in the context of spatial augmented reality in heavy machinery applications. © 2024 University of West Bohemia. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Teaching Methods For Sharing The Creation Of Electroacoustic Music With Inexperienced People 17

Teaching Methods For Sharing The Creation Of Electroacoustic...

引用

17th international conference on Interfaces and Human computer Interaction 2023, IHCI 2023, the 17th international conference on computer graphics, visualization, computer Vision and Image Processing 2023, CGVCVIP 2023 and 16th international conference on Game and Entertainment Technologies 2023, GET 2023

作者： Matsumoto, Miki Mashita, Takumi Arai, Soma Ohmura, Hidefumi Yaguchi, Hiroyuki Shibayama, Takuro Tokyo Denki University Ishizaka Hatoyama Hiki Saitama 350-0394 Japan Tokyo University of Science 2641 Yamazaki Noda Chiba278-0022 Japan Tokyo Collage of Music 1-9-1 Kamimeguro Meguro Tokyo153-0051 Japan

ISBN: (纸本)9789898704498

Our lab holds a workshop using computers to create electroacoustic music (EAM) for a variety of inexperienced people. Since EAM is positioned as an extension of contemporary music, which has a large philosophical component, it has not gained as many creators and listeners as popular music. The reason for this may be that, compared to music meant for entertainment, both the structure in music theory and the concepts in expressive practice create the impression among many people that EAMis difficult to understand. However, we observed that numerous people enjoy creating EAMin workshops. This may be because EAM is created not by following the rules of ordinary music theory, but by producing a montage of sound materials formed from fragments of recorded sounds along a computer timeline, allowing the listener to hear a near-perfect acoustic representation in real time through intuitive manipulation. Through our creative method, we taught participants to capture their impressions of fragmented acoustic materials using metaphorical adjective pairs such as 'high-low' and 'hard-soft' and to maintain the intensity of the contrast between them. This study is based on an analysis of the works created in university courses that share the same teaching techniques as our workshops. The analytical procedure of the present study was as follows: (1) We selected an 'excellent' completed piece of music. (2) We individually extracted the acoustic materials that made up the piece. (3) We used pairwise comparison to examine the participants' impressions of all acoustic materials used in the given piece. (4) We carried out an analysis to determine whether the original piece maintained a high degree of contrast in the impression of the acoustic materials, thereby validating our instructional technique, which we empirically derived from past workshops. © 2023 Proceedings of the international conferences on Interfaces and Human computer Interaction 2023, IHCI 2023;computer graphics, Visualiza

关键词： computer games

来源：评论

学校读者我要写书评

暂无评论

Synergistic Fusion of Multi-Contrast imaging and Computational Image Synthesis for Quadruple Contrast-Enhanced Images and Multi-Map Generation

Synergistic Fusion of Multi-Contrast Imaging and Computation...

引用

2024 international conference on Communication, computer Sciences and Engineering, IC3SE 2024

作者： Mishra, Poonam Khalaf, Hameed Hassan Arabi, Mohammed Yousif Al-Shaikhli, Taha Raad Applied Mathematics Aset Amity University Chhattisgarh Raipur India Al-Manara College For Medical Sciences Maysan Iraq College Of Computer National University Of Science And Technology Dhi Qar Iraq AL-Nisour University College Department Of Medical Laboratories Technology Baghdad Iraq

ISBN: (纸本)9798350366846

Accurate tissue maps and a wide range of imaging modalities are required for medical imaging assessments and therapies. Our exclusive technology employs multi-contrast imaging and cutting-edge computer image synthesis to produce high-quality multi-maps and pictures of body regions and disorders. This approach uses deep learning fusion and computational image synthesis to construct multi-maps of disease markers and tissue features from several imaging modalities. Quality inspection and validation assure the correctness of the images and multi-maps. In terms of memory, accuracy, precision, and other performance measures, our strategy surpassed all other approaches. Reliable data gathering and visualization of physiological structures may enhance patient outcomes and medical imaging technologies. Applying the research results to other clinical contexts necessitates confirming the findings with real clinical data. The technology available might help medical practitioners comprehend and analyse complicated biological systems. There may be personalized treatment regimens and diagnostic imaging. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

41st computer graphics international conference, CGI 2024

41st Computer Graphics International Conference, CGI 2024

引用

41st computer graphics international conference, CGI 2024

ISBN: (纸本)9783031820205

The proceedings contain 29 papers. The special focus in this conference is on computer graphics. The topics include: Reinforcement Learning Based Improved Seam Carving Using Special Point and Alpha Value for Optimal Content Preservation;shape Descriptor Guided Learning for Category-Level Object Pose Estimation;network Topology Recognition from Images via Window Detection;smart Clothing System for Arrhythmia Detection Based on Digital Twin Technology;ALFC-Point: Adaptive Laplacian Feature Convolution Network for 3D Point Cloud Understanding;An Improved YOLOv8-Based Rice Pest and Disease Detection;Pedestrian Detection in Foggy Weather Through YOLOv8 Based on FEAttention;the Establishment of a Hypoxia Cellular Morphology Model Based on Deep Convolutional Neural Networks and Intelligent Screening of Anti-hypoxia Drugs;End-to-End Transformer Architecture with Novel Ensemble Learning Method Integrating CT Scans and Clinical Narratives for Brain Stroke Diagnosis;TransSG: A Spatial-Temporal Transformer for Surgical Gesture Recognition;semi-Mamba: Improving Medical Image Segmentation via Semi-Automatic Mamba Network;a Real-Time Semantic Segmentation Network for Robotic Arm Grasp;MFENet: Multi-scale and Local Frequency Enhancement Network for Skin Lesion Classification;Mixed Reality Hologram Slicer (mxdR-HS): A Markerless Tangible User Interface for Interactive Holographic Medical Volume visualization;Edge Enhancement And Dual UNet Fusion Based GAN For Structure Preserving Stain Normalization;CF-Net: A Hybrid CNN-Random Forest Network for Depression Classification in Brain MRI;rectified Flow for Efficient Automatic Implant Generation;fast Mesh Generation in Multi-layer Lattice Boltzmann Simulation with Moving Boundaries;combining Stable Diffusion and Object Detection for Semi-automatic Environment Decoration;efficient Low-Polygon Building Model Generation with Opening Detection;realistic Image Super-Resolution with Generative Diffusion;Pencils of CGA for Voronoi and Power Dia

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Pupil Segmentation Network Based on Improved TransUNet 8

Research on Pupil Segmentation Network Based on Improved Tra...

引用

8th international conference on computer graphics and Virtuality, ICCGV 2025

作者： Jianting, Liu Huazhong, Xiang Zexi, Zheng Dawei, Zhang Songlin, Zhuang College of Health Sciences and Engineering University of Shanghai for Science and Technology Shanghai200093 China College of Mechanical Engineering University of Shanghai for Science and Technology Shanghai200093 China College of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9781510689213

To address the critical challenge of pupil segmentation accuracy in medical image analysis, this paper proposes an innovative pupil segmentation method based on an enhanced TransUNet deep neural network. The proposed architecture introduces three key improvements: a novel multi-kernel self-selective attention mechanism that optimizes local feature extraction through weighted fusion of different convolution modules;a modified cross-attention Transformer that enables efficient parallel processing of spatial information in both horizontal and vertical dimensions;and an advanced feature fusion module that effectively integrates global and local information through multi-scale feature weighting. Extensive experiments on the OpenEDS dataset demonstrate the method's superior performance, achieving state-of-the-art results with average precision of 97.7%, average recall of 97.41%, and average Dice coefficient of 98.15%. These significant improvements in segmentation accuracy not only advance the field of medical image analysis but also provide a robust foundation for applications in ophthalmological diagnosis, human-computer interaction, and cognitive science research. The proposed methodology offers valuable insights into designing efficient attention mechanisms for medical image segmentation tasks, contributing to both theoretical understanding and practical applications in healthcare imaging systems. © 2025 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Exploration of Reconstruction-based Computational Frameworks for graphics and visualization 3

A Comprehensive Exploration of Reconstruction-based Computat...

引用

3rd international conference for Advancement in Technology, ICONAT 2024

作者： Solanki, Madhav Singh Srikantha, H. Acharjya, Kalyan Sanskriti University Department of Computer Science and Engineering Uttar Pradesh Mathura India School of Engineering and Technology Department of Civil Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350354171

Reconstruction-primarily based computational frameworks offer a vital basis for photos and visualization. The conventional strategies used to generate visible representations of a given model depend closely upon analytically determined answers for the underlying geometry, making them tough, if no longer impossible, to increase for more complex systems. Therefore, it is beneficial to explore reconstruction-based methods as an alternative for tackling the various challenges associated with photographs and visualization. This paper offers a complete exploration of reconstruction-based computational frameworks for pictures and visualization. Via an intensive survey of different strategies and methods, the merits and downsides of every method are analyzed and compared to each other. Additionally, current literature is mentioned, presenting insights into furthering the development of reconstruction-primarily based methods. Finally, an evaluation of the important thing layout concerns is presented, concluding with destiny directions for research. Those encompass leveraging records-pushed strategies, specializing in robustness, and enabling actual-time overall performance. Normal, this paper provides a deep and well-rounded exploration of the potential of reconstruction-based computational frameworks for photos and visualization. It offers insights into existing literature and the destiny guidelines for studies in addition to a clear review of the one-of-a-kind strategies available. The authors provide a thorough analysis in their conclusions, paving the way for fruitful discussions and doubtlessly main to the development of stepped-forward techniques. © 2024 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：